Why: Compiled workflow critics could resend a prior prompt output after document duty or publication changed across separate model guards.
Evidence: RED cross-guard revocation and retry tests; go test ./... -count=1 and targeted go test -race passed locally before commit.
Impact: Bind materialized prompt bytes to the engine step attempt and responded model receipt; recheck current project sources and epochs before judging, failing closed for unproven or ambiguous output.
Refs: RDM two-trees stage5 W6; stage6 X1 public extension request; W6 independent review P1.
Why: Revoked project material could remain in later model turns, and plugin Audit could impersonate a model-input manifest.
Evidence: SELF red tests reproduced both paths; updated project revocation, trusted receipt, migration, and entrypoint tests pass locally with go test ./... -count=1 and targeted race checks.
Impact: Rebuild direct model requests after scope changes, sanitize or block unproven generic history, omit legacy project injections, and persist manifests in a dedicated state-checked table.
Refs: TT-C02 TT-C03 TT-C04; stage5 W6; review P1 stale context and manifest provenance
Why: Project work currently reaches model calls without current authorized project facts or a persisted input receipt.
Evidence: SELF go test ./... -count=1, targeted go test -race for W6 paths, go vet ./..., and CGO_ENABLED=0 go build ./cmd/agent-system passed on this change set.
Impact: Add optional X1 interfaces, trusted persisted work-task binding, request-scoped context injection, evidence reauthorization, and attempted/responded/unknown manifests. Existing non-project behavior stays available.
Refs: TT-C01 TT-C02 TT-C03 TT-C04; stage5 W6; Dev stage6 X1 public extension request r1
Why:
Legacy project streams replayed upload filenames and parser metadata to newly
authorized members even though the underlying cards remained owner-only.
Evidence:
SELF real HTTP red regressions exposed legacy replay, spoofed sharing claims,
private-history pagination, and live delivery after membership removal. The
affected packages, uncached full Backend suite, isolated PostgreSQL Store suite,
and agent-system build pass after applying the event boundary.
Impact:
Registered lifecycle streams resolve trusted resource ownership and require an
internal publication proof for cross-owner delivery. Event and proof commit in
one transaction; v30 adds an additive SQLite/PostgreSQL sidecar without granting
access to historical events. Seen and visible cursors remain separate, revoked
members leave live streams, and unregistered base behavior remains compatible.
The storage migration tool preserves the new proof rows.
Refs:
project-member-access-implementation-plan.md Task 1 / R5; authorized legacy SSE
privacy follow-up; project-member-composed-legacy-project-history.json
Why:
Nested unchanged credential masks left empty parents that looked like managed
subtree overwrites. Shared members also hit an owner-only upload guard, while
upload ingestion cards could disclose private filenames and parser metadata.
Evidence:
SELF independent nested-mask probe, HTTP nested/mixed writeback, member upload,
project card privacy and authorization-change regressions failed before each fix
and passed after it. Affected settings/server suite passed; exact final-object
build and independent replay remain delivery gates owned by the task coordinator.
Impact:
Prune only parents emptied by ignored masks; explicit empty/real managed writes
stay rejected. Registered uploads check live work and trusted project existence,
keep originals owned by the actor, and recheck before persistence. Suppress only
upload project cards when no private stream exists; explicit structure cards and
unregistered upload behavior remain available.
Refs:
Dev project-member-access plan r1 Task 1/R5; independent nested mask P2;
2026-10-13 composed member-upload and private project-stream acceptance findings
Why:
Legacy project metadata can contain credentials outside the settings scope table.
Sharing raw projection settings exposed them, and generic project PATCH bypassed
the system-managed path guard already enforced by project settings endpoints.
Evidence:
SELF member Host regression failed before the fix. The fixed 4f72aaf server
baseline overlay reproduced HTTP metadata leakage and managed PATCH returning 200.
SELF shared Host-to-HTTP, immutable mask, dotted/schema/fallback, public mutation
and atomic managed-write regressions passed; uncached full suite, isolated PG
Store suite and static build passed. Independent delta replay remains a gate.
Impact:
Registered lifecycle metadata returns detached credential-masked views while
preserving service/configuration keys and persisted data. Generic project PATCH
shares the existing managed validator before rename or settings mutation; allowed
metadata key shapes and raw owner-only management lookups remain available.
Refs:
Dev project-member-access plan r1 Task 1 and R5; approved hard secret boundary;
2026-10-13 shared project metadata review follow-up
Why:
Membership could be revoked while a tool waited for confirmation or a queued
HITL reply waited for consumption. Publication replacement also crossed an
empty project scope or another plugin's source namespace for the same Ref.
Evidence:
SELF replay of all four independent review reproductions failed before the
fix and passed unchanged afterward. Committed regressions cover direct and
queued HITL, yes/session confirmation, direct artifact writes, protected vectors,
exact empty project scopes, literal wildcard IDs and unregistered compatibility.
SELF uncached go test ./..., isolated PostgreSQL Store tests and static build passed.
Impact:
Recheck trusted live owner/project authorization when HITL resumes and at write
boundaries. Registered publishers replace only exact owner/project/ref/plugin
rows and vectors; ordinary unregistered publication semantics are preserved.
Refs:
Dev project-member-access implementation plan r1 Task 1; independent Backend
review findings against b9bea5bee0
Why:
Higher-ranked private rows could exhaust SQL candidate limits and hide an
otherwise authorized published slice from a member's current-project search.
Evidence:
SELF TestAuthorizedKnowledgeFiltersBeforeTopK failed with no shared hits before
the change and passed after it. SELF go test ./... and the isolated PostgreSQL
Store suite passed; independent replay and current-HEAD CI remain owner gates.
Impact:
Scan the resource-authorized shared fulltext path until enough allowed results
are found. Preserve ordinary legacy retrieval candidate limits and semantics.
Refs:
Dev project-member-access plan r1 Task 1; R5 published knowledge availability
Why:
Shared project reads previously doubled as write permission, project mutations
bypassed the domain lifecycle, and coarse retrieval shared private resources.
Evidence:
SELF red-before-implementation logs cover projection, lifecycle, private work,
resource filtering, canonical retrieval scope, publication source and namespace.
SELF go test ./..., isolated PostgreSQL go test ./internal/store -count=1,
and CGO_ENABLED=0 go build ./cmd/agent-system passed; task owner owns replay/CI.
Impact:
Add optional actor-scoped projection/lifecycle capabilities; registered providers
control public lifecycle and live work. Preserve owned conversation history and
ordinary unregistered behavior. Authorize knowledge by stored ID/source, map
current host scopes through trusted service metadata, and filter artifact lists.
Refs:
Dev project-member-access implementation plan r1 Task 1; approved design r0.1;
2026-10-13 trusted publication Source hardening ruling
Why: The login recovery contract leftovers and KTD12/KTD14 require:
concurrent same-name account creation must not overwrite the winner,
first-admin bootstrap must serialize across processes, the redeem
endpoint backoff must be shared across instances, revoked API keys
must close established SSE streams, and CLI credentials need an
env-DSN path plus a non-interactive 0600 file delivery mode.
Evidence: go test ./... green; new tests cover 16-way concurrent
create (1 win/15 conflict, winner credentials intact), 8-way
concurrent bootstrap (single admin, refuse takeover after), redeem
guard shared across two store handles on one DB, SSE stream closed
after key revocation within the recheck window, and HTTP 429 after
the failure cap (SELF worktree run; CI is the GATE, PG via test-pg).
Impact: Migration v29 (redeem_attempts); CreateAccount becomes a
single-row INSERT with unique-violation conflict; BootstrapFirstAdmin
advisory-locks (PG) / rechecks (SQLite) and commits admin+key+audit in
one transaction; SSE revalidation covers API-key streams; redeem
backoff moves to the shared DB; CLI gains AGENT_SYSTEM_DSN fallback
and --out file delivery for create/reset-password/issue-login-key/
bootstrap-admin.
Refs: docs/svc-deploy/2026-10-13-login-recovery-contract.md leftovers;
proposal r2 KTD12/KTD14/R5/R11.
Why: Since the system-managed settings change (#188), runtime.* writes
at the user scope are rejected, so the mock startup flag failed with
"system-managed settings require admin" and the serve process never
became healthy - the Dev multi-instance integration regression.
Evidence: go build ok; internal/app and internal/settings suites green
(SELF); the Dev composite CI on the follow-up PR re-runs
make test-multi-instance against this fix (GATE).
Impact: The mock startup flag now seeds runtime.mock via MergeSystem
(trusted operator input, effective for every tenant through the
Effective merge chain); no HTTP surface changes.
Refs: Dev PR #508; backend #188.
Why: The 2026-10-13 login recovery contract (Dev docs/svc-deploy/
2026-10-13-login-recovery-contract.md, plan item 6.7) requires that
established SSE connections stop receiving private events once a
password write destroys their session.
Evidence: go test ./... green; TestSSESessionInvalidationClosesStream
streams over a real HTTP server, invalidates the session via
AdminResetUserPassword, and asserts the stream terminates with the
session-expired marker within the recheck window (SELF, worktree run).
Impact: Session-authenticated event streams revalidate at a 15s
heartbeat cadence (package var, shortened in tests) and terminate on
invalidation; API-key streams are unchanged (key revocation is separate).
EventSource reconnects are rejected by the auth middleware.
Refs: Dev PR #504; login recovery contract section 6.7.
Why: The login recovery contract (2026-10-13) requires admin-issued
one-time keys, in-transaction revalidation of restricted sessions, a
login race guard, and audited password writes; the previous
implementation validated sessions outside the change-password
transaction and let stale password verifications create sessions.
Evidence: go test ./... green (SQLite); store tests switch to
openTestStore so the CI test-pg job covers real PostgreSQL, including
100-way concurrent redeem single-winner and auth-version race cases
(SELF, local run).
Impact: New migration v28 (users/sessions.auth_version,
account_events). New admin endpoints POST/GET
/api/admin/users/{owner}/login-keys and DELETE
.../login-keys/{id}. Login binds session creation to the verified
auth version and creates restricted sessions for must-change accounts;
redeem gains per-IP backoff; cookies gain Secure under TLS; active
change-password and admin/CLI resets become single transactions that
bump auth_version, revoke keys and sessions, and write audit events.
Refs: modules/documents/docs/proposals/2026-10-12-svc-unified-deploy-and-login-key.md r2; Dev task feature/svc-login-recovery-flow
Why: an unset object-storage endpoint passed a typed nil into the store and artifact upload panicked.
Evidence: GATE vet-and-test run 2783 job 4031 success on 46073d30a5. Independent review approved with no blockers.
Impact: unconfigured stores fall back to the local artifacts directory. Configured S3 is unchanged.
Refs: #186
Why: an unset S3 client passed through the Store interface is not a nil interface, so uploads panic instead of using the local artifact directory.
Evidence: TestIsNil and TestFinishOpenTypedNilS3UsesLocalArtifacts failed before this change and pass after it. The PostgreSQL case skips unless AGENT_PG_TEST_DSN is set.
Impact: only an unset blob store falls back; a constructed S3 or local store is unchanged.
Refs: internal/blobstore/blobstore.go internal/store/store.go
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: identity probes must open an existing database without creating or migrating it, and DSN must stay out of argv.
Evidence: GATE ci / vet-and-test success on 0f192a4813, run 2625 job 3782.
Impact: version --json carries schema target and compat floor; unknown top-level commands exit 2.
Refs: #184
Why: main gained AGENT_SYSTEM_DSN fallback in #182 after this branch
was cut. Both changes touch identity DSN parsing.
Evidence: go test ./pkg/identity/ ./internal/store/ ./cmd/agent-system/ for the identity, schema, and unknown-subcommand cases passed after the resolution.
Impact: keeps open-existing identity mode and the 0600 dsn file. Environment
DSN still wins when --dsn is absent, via ResolveDSN.
Refs: Backend #182; recovery plan r3.1 D1
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: a rollback can only be safe when the candidate says which schema it
will migrate to and whether older binaries can still read that schema.
A new migration that forgets to register that fact must fail the test.
Evidence: go test ./internal/store/ ./pkg/identity/ -run 'TestMigrationCompat|TestCapabilities' passed.
Impact: version --json and identity capabilities include schema.target and
schema.compatFloor. Every migration version is listed in
migrationBreaksOldReaders. Current versions do not break old readers, so
the floor stays 0.
Refs: recovery plan r3.1 D2
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: identity ensure/verify went through the normal store open, which
creates a database and runs migrations. A deploy gate that calls the
candidate before stopping the old service could migrate production
ahead of the switch, and a missing database was turned into an empty one.
Evidence: go test ./pkg/identity/ ./internal/store/ ./cmd/agent-system/ -run 'TestCapabilities|TestEnsure|TestVerify|TestDSN|TestUsage|TestSystemIdentity|TestOpenIdentity|TestUnknownSubcommand' passed in this worktree.
Impact: identity CLI refuses a missing file or a missing agent_system_identity table, does not migrate, reads DSN from the environment or a 0600 file, and version --json plus identity capabilities emit one capability document. Unknown top-level commands exit 2.
Refs: recovery plan r3.1 D1; Dev feature/svc-d1-identity-flow
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: svc.sh delivers database credentials via environment per G1-7
(command lines are visible to every process on the host), but identity
ensure/verify only accepted --dsn on the command line for pg-bound
instances.
Evidence: go test ./pkg/identity/... ok; build ok.
Impact: --dsn remains highest priority, then AGENT_SYSTEM_DSN, then
embedded SQLite; no storage changes.
Refs: Dev U3 (real-combination CI gates); G1-7 credential discipline.
Why: runIdentity lived in cmd/agent-system package main, so downstream
combination binaries (Agent-System-RDM) cannot reuse it and their unknown
subcommands fall into the serve path; the 2026-10-12 rdm1/rdmcand batch
update failures traced back to that capability gap.
Evidence: go test ./pkg/identity/... ok; CGO_ENABLED=0 go build ok;
behavioral probes (usage rc=2, capabilities v1, ensure/verify roundtrip)
recorded in the PR.
Impact: identity semantics unchanged for the base binary; adds
identity capabilities (v1) and usage-on-unknown contract shared by all
products; no storage changes.
Refs: Dev PR #474 (svc.sh candidate gate); user root-cause report
2026-10-12 U1 (shared identity interface).
Why: Stop showing raw task text as progress and stop lighting the
done lamp on failed background runs (U1 whitelist).
Evidence: go test ./internal/runmgr/ -count=1
Impact: create/promote/finish card bodies; material queue status text.
Refs: fast-slow-channel-display-u1-plan W2; Core ba289e7
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: TestMaterialIntakeAttachmentOnlyLifecycle flaked when waiting on
systemTexts; deliverNotices runs before defer materialKeyRelease, so
done-dedup still saw the in-memory key and returned pending.
Evidence: go test ./internal/runmgr/ -run TestMaterialIntakeAttachmentOnlyLifecycle -count=20
Impact: Aligns the wait with materialExisting gates; no production change.
Refs: fix/material-intake-lifecycle-flake
Co-authored-by: Cursor <cursoragent@cursor.com>
weichen
weichen